Finite sample properties of estimators for autoregressive moving average models

Ansley, Craig F.; Newbold, Paul

doi:10.1016/0304-4076(80)90013-5

Cited by 137 publications

(77 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ansley and Newbold [1980), Harvey [1981] and Davidson [1981] all report finding a probability mass at exactly unity for this maximum, particularly large when the true root is unity but also present when it is considerably less than unity.…”

Section: Resultsmentioning

confidence: 99%

Are Output Fluctuations Transitory?

Campbell¹,

Mankiw²

1986

212

249

View full text Add to dashboard Cite

Are Output Fluctuations Transitory? ABSTRACT According to the conventional view of the business cycle, fluctuations in output represent temporary deviations from trend. The purpose of this paper is to question this conventional view. If fluctuations in output are dominated by temporary deviations from the natural rate of output, then an unexpected change in output today should not substantially change one's forecast of output in, say, ten or twenty years. Our examination of quarterly post-war United States data leads us to be skeptical about this implication. We find that a unexpected change in real GNP of one percent should change one's forecast by over one percent over a long horizon. While it is obviously imprudent to make definitive judgments regarding theories on the basis of one stylized fact alone, we believe that the great persistence of output shocks documented in this paper is an important and often neglected feature of the data that should more widely be used for evaluating theories of economic fluctuations.

show abstract

Section: Resultsmentioning

confidence: 99%

Are Output Fluctuations Transitory?

Campbell¹,

Mankiw²

1986

212

249

View full text Add to dashboard Cite

show abstract

“…Tbere is a small recent literature analyzing tbe properties of maximum likelihood estimates of ARMA model parameters [Plosser and Schwert, 1977;Ansley and Newbold, 1980;Davidson, 1981;Harvey, 1981;Pesaran, 1981;Sargan and Bhargava, 1983]. Wben the moving average roots are strictly less tban unity, the maximum likelihood estimator is consistent and asymptotically normal.…”

Section: Econometric Issues In Estimating Arma Modelsmentioning

confidence: 99%

“…Ansley and Newbold [1980], Harvey [1981], and Davidson [1981] all report finding a probability mass at exactly unity, particularly large when the true root is unity but also present when it is considerably less than unity. This occurs because tbe observational equivalence ofB* and 1/B* discussed above causes the sample likelihood function to be fiat at 9 = 1.…”

Section: Econometric Issues In Estimating Arma Modelsmentioning

confidence: 99%

Are Output Fluctuations Transitory?

Campbell¹,

Mankiw²

1987

The Quarterly Journal of Economics

586

View full text Add to dashboard Cite

According to the conventional view of the businesB cycle, fluctuations in output represent temporary deviations from trend. The purpose of this paper is to question this conventional view. If fluctuations in output are dominated by temporary deviations from the natural rate of output, then an unexpected change in output today should not substantially change one's forecast of output in, say, five or ten years. Our examination of quarterly postwar United States data leads us to be skeptical ahout this implication. The data suggest that an unexpected change in real GNP of 1 percent should change one's forecast by over 1 percent over a long horizon.

show abstract

“…However, they di er to some extent from Ansley and Newbold(1980). They demean the data by the population mean while we use the sample mean { as is commonly done { leading to a more or less pronounced asymmetric behavior of the time domain ML estimates at parameter values associated with real roots close to +1 on one hand, and 1 on the other.…”

Section: Small Sample Behavior Of the Estimatorsmentioning

confidence: 99%

Maximum Likelihood Estimators for ARMA and ARFIMA Models: A Monte Carlo Study

Hauser

1998

SSRN Journal

View full text Add to dashboard Cite

Finite sample properties of estimators for autoregressive moving average models

Cited by 137 publications

References 15 publications

Are Output Fluctuations Transitory?

Are Output Fluctuations Transitory?

Are Output Fluctuations Transitory?

Maximum Likelihood Estimators for ARMA and ARFIMA Models: A Monte Carlo Study

Contact Info

Product

Resources

About